Borrowing it
Nothing to install: this file belongs to gpt-cmdr/ras-commander. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/gpt-cmdr/ras-commander/main/.claude/skills/technical-writing-auditor/SKILL.mdgit clone --depth 1 https://github.com/gpt-cmdr/ras-commanderWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/gpt-cmdr/ras-commander/technical-writing-auditor)<a href="https://agentmods.dev/skills/gpt-cmdr/ras-commander/technical-writing-auditor"><img src="https://agentmods.dev/badge/skills/gpt-cmdr/ras-commander/technical-writing-auditor/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/gpt-cmdr/ras-commander/technical-writing-auditor"><img src="https://agentmods.dev/badge/skills/gpt-cmdr/ras-commander/technical-writing-auditor.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00070 | $0.00875 |
| Opus 5.5 | $0.00028 | $0.00350 |
| Sonnet 5.5 | $0.00014 | $0.00175 |
| Haiku 4.5 | $0.00007 | $0.00088 |
Grade A, and why
technical-writing-auditor scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 25d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 37 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Technical Writing Auditor
Review repository-maintained technical text and intended contributions across RAS Commander. HEC is the primary source for HEC-RAS terminology and documented behavior. RAS Commander is an independent open source project that complements HEC's work; it must not imply affiliation, endorsement, certification, or vendor support. Published HEC references are passive citations and links.
RAS Commander is authoritative about its own supported capabilities and reproducible observations. Match the explanation to the audience. Do not demand HEC endorsement or citations for project evidence, suppress original findings, or introduce unnecessary hedging into established results.
Load the writing contract
Find the repository root and read the nearest AGENTS.md for the selected surface. Read the concise guide. Read the relevant sections of the extended standard for terminology, technical claims, references, or content-specific review. These repository guides are canonical; do not maintain a second glossary inside this skill.
Use the audit protocol for coverage, checks, findings, and output. Read it before an audit or editing pass. Existing repository contracts take precedence over imported style conventions; report a conflict rather than overriding protected behavior.
Working boundaries
-
Apply this standard only to repository-maintained RAS Commander content and intended contributions. Do not audit or enforce it on external user artifacts merely because they use RAS Commander or this skill is installed. If a user explicitly requests external writing assistance, follow their scope and editorial requirements; identify repository-derived suggestions as optional advice.
-
Default to review of the requested diff/files. A broad audit must inventory surfaces and declare sampling; reading a sample does not establish whole-library compliance.
-
Review authored prose, not every source token. Include notebook Markdown, docstrings, narrative comments, UI/log/exception text, and captions when they are in scope. Saved outputs, generated pages, vendor files, code literals, and legal text have separate source/compatibility constraints.
-
Consult official HEC documents for consequential HEC claims. Use implementation/schema/evidence for library behavior and provider references for external data. Prefer the applicable version over a changing
latestpage. A search snippet or inaccessible source is not confirmed full-text evidence. -
Passive references are ordinary reader-activated links/citations. Research browsing is permitted. Do not introduce runtime HEC-page requests, live embeds, scraped/mirrored documentation, or automated HEC contact as part of a citation.
-
Preserve identifiers, labels, values, units, formulas, signs, timestamps, citations, and uncertainty. Confirm a technical correction against evidence; otherwise report it as unresolved. Do not invent thresholds, compatibility, support, results, or source metadata.
-
Select register by task. Direct instructions are appropriate in tutorials; objective technical prose is appropriate in reports. Do not globally replace flow, stage, storm, validation, SI units, or source titles using FIM-specific lexical rules.
-
Review by default. When revision is authorized, edit the canonical source and make supported changes. Message/identifier/code changes require compatibility and behavior review. Do not execute HEC-RAS, run notebooks, publish, contact HEC, or merge as a side effect of a writing audit.
What ships with it
1 file beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 25d ago First seen · 37 lines · 70 tokens per session scan A 74d711321034
technical-writing-auditor is a skill published in the GitHub repository gpt-cmdr/ras-commander (88 stars, last pushed today), licensed MIT. It adds 70 tokens to every session and 875 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-04.
Other skills, from other repositories
autoreview
Structured code review through the shared OpenClaw agent-skills installation.
omh-code-review
This is an OMH code-review workflow skill, projected for Agent Skills hosts (Claude Code, Codex, Cursor, opencode, OpenClaw, pi).
revdiff-plan
Review the last Codex assistant message (plan, analysis, or proposal) with inline annotations in a TUI overlay. Extracts the most recent response from Codex rollout files and opens it in revdiff for review and annotation. Activates on "revdiff-plan", "review plan with revdiff", "annotate plan", "review last response"…
explore-unknowns
Guide the user through a quadrant walk that maps the unknowns of a task — open by listing the known knowns, then work through known unknowns, unknown knowns, and unknown unknowns one stage at a time, ending with a complete four-quadrant map in the user's hands. Use when a request is ambiguous or underspecified, the…
re0-merge
Review and land an external contribution the way this suite does: gate it against the thesis, land it with the author's credit intact, complete a new skill rather than merging it raw, then approve, credit, and explain before closing. Use when reviewing a pull request, as any collaborator or maintainer, not only the…
asplos-writing-style
Use when drafting or revising ASPLOS prose — engineering the first two pages that rapid review actually reads, stating the cross-layer insight as one quotable sentence, structuring per-layer mechanism sections, writing bounded claims, and fitting everything into 11 self-contained pages that include figures and…